paper-with-me

Papers

DIMAL: Deep Isometric Manifold Learning Using Sparse Geodesic Sampling

2017-11-16 · Gautam Pai, Ronen Talmon, Alex Bronstein, Ron Kimmel

This paper explores a fully unsupervised deep learning approach for computing distance-preserving maps that generate low-dimensional embeddings for a certain class of manifolds. We use the Siamese configuration to train a neural network to solve the problem of least squares multidimensional scaling for generating maps that approximately preserve geodesic distances. By training with only a few landmarks, we show a significantly improved local and nonlocal generalization of the isometric mapping as compared to analogous non-parametric counterparts. Importantly, the combination of a deep-learning framework with a multidimensional scaling objective enables a numerical analysis of network architectures to aid in understanding their representation power. This provides a geometric perspective to the generalizability of deep learning.

📄 PDF Abstract BibTeX arXiv:1711.06011

Code (1)

paigautam/DIMAL 공식 구현 pytorch

Tasks

Deep Learning

Similar Papers 제목 키워드 기반

Parallel Transport Unfolding: A Connection-based Manifold Learning Approach

2018-06-23 · Max Budninskiy, Glorian Yin, Leman Feng, Yiying Tong 외

Manifold learning offers nonlinear dimensionality reduction of high-dimensional datasets. In this paper, we bring geometry processing to bear on manifold learning by introducing a new approach based on metric connection …

Dimensionality Reduction

Turing approximations, toric isometric embeddings & manifold convolutions

2021-10-05 · P. Suárez-Serrato

Convolutions are fundamental elements in deep learning architectures. Here, we present a theoretical framework for combining extrinsic and intrinsic approaches to manifold convolution through isometric embeddings into to…

Uniform Interpolation Constrained Geodesic Learning on Data Manifold

2020-02-12 · Cong Geng, Jia Wang, Li Chen, Wenbo Bao 외

In this paper, we propose a method to learn a minimizing geodesic within a data manifold. Along the learned geodesic, our method can generate high-quality interpolations between two given data samples. Specifically, we u…

Translation

Classification of Hyperspectral Imagery on Embedded Grassmannians

2015-02-03 · Sofya Chepushtanova, Michael Kirby

We propose an approach for capturing the signal variability in hyperspectral imagery using the framework of the Grassmann manifold. Labeled points from each class are sampled and used to form abstract points on the Grass…

ClassificationGeneral Classification

Shape analysis of framed space curves

2018-07-10 · Tom Needham

In the elastic shape analysis approach to shape matching and object classification, plane curves are represented as points in an infinite-dimensional Riemannian manifold, wherein shape dissimilarity is measured by geodes…